INDEX

Explanations

coding-related terms and operations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Code snippets with specific syntax

np_acts-logits-general · gemini-2.0-flash

variable assignments like `key = value`

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.40

 './../

-0.39

 bast

-0.37

 assi

-0.37

actionMode

-0.36

ℚ

-0.36

casian

-0.36

removeFrom

-0.35

<%@

-0.35

../

-0.34

POSITIVE LOGITS

didSet

0.68

makeText

0.64

TagMode

0.60

SharedCtor

0.58

providedIn

0.58

figsize

0.57

internalType

0.55

mappedBy

0.55

AxisAlignment

0.50

 cuna

0.50

Activations Density 0.389%

coding-related terms and operations

Code snippets with specific syntax

variable assignments like `key = value`

No Comments

No Known Activations